{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:CIEZAZVBSVQQRE4256BYL6G3LQ","short_pith_number":"pith:CIEZAZVB","schema_version":"1.0","canonical_sha256":"12099066a1956108939aef8385f8db5c007f7849095ebad9be4163f3c1b265c8","source":{"kind":"arxiv","id":"2107.10253","version":1},"attestation_state":"computed","paper":{"title":"Demonstration-Guided Reinforcement Learning with Learned Skills","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Joseph J. Lim, Karl Pertsch, Youngwoon Lee, Yue Wu","submitted_at":"2021-07-21T17:59:34Z","abstract_excerpt":"Demonstration-guided reinforcement learning (RL) is a promising approach for learning complex behaviors by leveraging both reward feedback and a set of target task demonstrations. Prior approaches for demonstration-guided RL treat every new task as an independent learning problem and attempt to follow the provided demonstrations step-by-step, akin to a human trying to imitate a completely unseen behavior by following the demonstrator's exact muscle movements. Naturally, such learning will be slow, but often new behaviors are not completely unseen: they share subtasks with behaviors we have pre"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2107.10253","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-07-21T17:59:34Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"effe37b82ff1c7b90ae8726bcc43e9d9d1ea65c4aaef17bfaa8ee2686df306c7","abstract_canon_sha256":"f03664dc093564893547be27c98497109fbdcca7258617a6b7c61b3514ca3077"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:59:50.407462Z","signature_b64":"walmPgplrsN/vWFKfBQaW6qrq/ZTAIq1L9v9jFDgaTjtsCKGLaphAT5IFpDq6R5QtwCfckIhCySq+K8PEegUAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"12099066a1956108939aef8385f8db5c007f7849095ebad9be4163f3c1b265c8","last_reissued_at":"2026-07-05T02:59:50.406987Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:59:50.406987Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Demonstration-Guided Reinforcement Learning with Learned Skills","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Joseph J. Lim, Karl Pertsch, Youngwoon Lee, Yue Wu","submitted_at":"2021-07-21T17:59:34Z","abstract_excerpt":"Demonstration-guided reinforcement learning (RL) is a promising approach for learning complex behaviors by leveraging both reward feedback and a set of target task demonstrations. Prior approaches for demonstration-guided RL treat every new task as an independent learning problem and attempt to follow the provided demonstrations step-by-step, akin to a human trying to imitate a completely unseen behavior by following the demonstrator's exact muscle movements. Naturally, such learning will be slow, but often new behaviors are not completely unseen: they share subtasks with behaviors we have pre"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.10253","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2107.10253/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2107.10253","created_at":"2026-07-05T02:59:50.407044+00:00"},{"alias_kind":"arxiv_version","alias_value":"2107.10253v1","created_at":"2026-07-05T02:59:50.407044+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.10253","created_at":"2026-07-05T02:59:50.407044+00:00"},{"alias_kind":"pith_short_12","alias_value":"CIEZAZVBSVQQ","created_at":"2026-07-05T02:59:50.407044+00:00"},{"alias_kind":"pith_short_16","alias_value":"CIEZAZVBSVQQRE42","created_at":"2026-07-05T02:59:50.407044+00:00"},{"alias_kind":"pith_short_8","alias_value":"CIEZAZVB","created_at":"2026-07-05T02:59:50.407044+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.03201","citing_title":"Reinforcement Learning from Cross-domain Videos with Video Prediction Model","ref_index":30,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CIEZAZVBSVQQRE4256BYL6G3LQ","json":"https://pith.science/pith/CIEZAZVBSVQQRE4256BYL6G3LQ.json","graph_json":"https://pith.science/api/pith-number/CIEZAZVBSVQQRE4256BYL6G3LQ/graph.json","events_json":"https://pith.science/api/pith-number/CIEZAZVBSVQQRE4256BYL6G3LQ/events.json","paper":"https://pith.science/paper/CIEZAZVB"},"agent_actions":{"view_html":"https://pith.science/pith/CIEZAZVBSVQQRE4256BYL6G3LQ","download_json":"https://pith.science/pith/CIEZAZVBSVQQRE4256BYL6G3LQ.json","view_paper":"https://pith.science/paper/CIEZAZVB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2107.10253&json=true","fetch_graph":"https://pith.science/api/pith-number/CIEZAZVBSVQQRE4256BYL6G3LQ/graph.json","fetch_events":"https://pith.science/api/pith-number/CIEZAZVBSVQQRE4256BYL6G3LQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CIEZAZVBSVQQRE4256BYL6G3LQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CIEZAZVBSVQQRE4256BYL6G3LQ/action/storage_attestation","attest_author":"https://pith.science/pith/CIEZAZVBSVQQRE4256BYL6G3LQ/action/author_attestation","sign_citation":"https://pith.science/pith/CIEZAZVBSVQQRE4256BYL6G3LQ/action/citation_signature","submit_replication":"https://pith.science/pith/CIEZAZVBSVQQRE4256BYL6G3LQ/action/replication_record"}},"created_at":"2026-07-05T02:59:50.407044+00:00","updated_at":"2026-07-05T02:59:50.407044+00:00"}